WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generation

TL;DR

WorldGenBench is a new benchmark for evaluating text-to-image models' ability to incorporate world knowledge and reasoning, revealing current strengths and gaps in state-of-the-art systems.

Contribution

Introduces WorldGenBench, a comprehensive benchmark with a Knowledge Checklist Score to assess reasoning and knowledge grounding in T2I models.

Findings

Diffusion models outperform other open-source methods.

Proprietary models like GPT-4o show stronger reasoning capabilities.

Current models still lack deep understanding and inference abilities.

Abstract

Recent advances in text-to-image (T2I) generation have achieved impressive results, yet existing models still struggle with prompts that require rich world knowledge and implicit reasoning: both of which are critical for producing semantically accurate, coherent, and contextually appropriate images in real-world scenarios. To address this gap, we introduce \textbf{WorldGenBench}, a benchmark designed to systematically evaluate T2I models' world knowledge grounding and implicit inferential capabilities, covering both the humanities and nature domains. We propose the \textbf{Knowledge Checklist Score}, a structured metric that measures how well generated images satisfy key semantic expectations. Experiments across 21 state-of-the-art models reveal that while diffusion models lead among open-source methods, proprietary auto-regressive models like GPT-4o exhibit significantly stronger reasoning and knowledge integration. Our findings highlight the need for deeper understanding and inference capabilities in next-generation T2I systems. Project Page: \href{https://dwanzhang-ai.github.io/WorldGenBench/}{https://dwanzhang-ai.github.io/WorldGenBench/}